Optimizing Energy-Efficient Task Offloading in Edge Computing: A Hybrid AI-Based Approach

Edge computing has emerged as a pivotal technology for managing computational workloads in latency-sensitive applications by offloading tasks from resource-constrained Internet of Things (IoT) devices to nearby edge servers. However, optimizing task offloading while ensuring energy efficiency remains a significant challenge. This paper proposes a Hybrid AI-Based Task Offloading (HATO) model, integrating Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically allocate computational resources while minimizing energy consumption. The HATO framework formulates task offloading as a multi-objective optimization problem, considering factors such as device workload, network latency, edge server availability, and energy constraints. Experimental evaluations demonstrate that the proposed model achieves a 27.3% reduction in energy consumption, a 19.6% improvement in task completion time, and a 31.2% enhancement in overall edge server utilization compared to conventional heuristic-based methods. The reinforcement learning module adapts task offloading strategies in real-time, ensuring optimal computational load balancing while minimizing latency. The proposed Hybrid AI-Based Approach outperforms baseline models in diverse edge computing scenarios, making it a scalable and efficient solution for next-generation IoT applications.